commit 42c78c4bb0fbd745a7a8ad8e50128382cc216f8b Author: ModelHub XC Date: Tue Jun 2 11:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BehChat-v0.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0fe6a10 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.f16.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v0.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BehChat-v0.3.IQ4_XS.gguf b/BehChat-v0.3.IQ4_XS.gguf new file mode 100644 index 0000000..bbb6b32 --- /dev/null +++ b/BehChat-v0.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b6468671c0d2ed2b912aaa4f3ced72964dbd4d06b326e42db3d845f7df9c907 +size 4593298528 diff --git a/BehChat-v0.3.Q2_K.gguf b/BehChat-v0.3.Q2_K.gguf new file mode 100644 index 0000000..7cf5f20 --- /dev/null +++ b/BehChat-v0.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1238015a6118595e779e66de2a8fdcd69595d0ade0eddb07343de4690b6cbd +size 3281734752 diff --git a/BehChat-v0.3.Q3_K_L.gguf b/BehChat-v0.3.Q3_K_L.gguf new file mode 100644 index 0000000..463f6b9 --- /dev/null +++ b/BehChat-v0.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9799bbd7c7150c9f0f246ab3c6de41c6adc0895d7d339bff01383afaca530a +size 4431395936 diff --git a/BehChat-v0.3.Q3_K_M.gguf b/BehChat-v0.3.Q3_K_M.gguf new file mode 100644 index 0000000..8cfbe75 --- /dev/null +++ b/BehChat-v0.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df184da6918ca81a611e4c07126fdece4885e4dd26b5791b7850b6cb59e3073 +size 4124163168 diff --git a/BehChat-v0.3.Q3_K_S.gguf b/BehChat-v0.3.Q3_K_S.gguf new file mode 100644 index 0000000..ea78694 --- /dev/null +++ b/BehChat-v0.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c030f6c16a45f991ea8b4946f42b6bcd094867bf2247d776712e58d5e89843 +size 3769613408 diff --git a/BehChat-v0.3.Q4_K_M.gguf b/BehChat-v0.3.Q4_K_M.gguf new file mode 100644 index 0000000..568a4be --- /dev/null +++ b/BehChat-v0.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd77883caf7a70068c324ce667d8baa47503a9280dc2a95226a57630920273e +size 5027785824 diff --git a/BehChat-v0.3.Q4_K_S.gguf b/BehChat-v0.3.Q4_K_S.gguf new file mode 100644 index 0000000..23a776f --- /dev/null +++ b/BehChat-v0.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec0d380f949a4e355d2555582f6f1313b73a95ae0ba642e026993f9094a50d0 +size 4802014304 diff --git a/BehChat-v0.3.Q5_K_M.gguf b/BehChat-v0.3.Q5_K_M.gguf new file mode 100644 index 0000000..c249040 --- /dev/null +++ b/BehChat-v0.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a09908587f1ecd06150aed3df1add4b36f1c4477132f9b91f48370f43a905b4 +size 5851114592 diff --git a/BehChat-v0.3.Q5_K_S.gguf b/BehChat-v0.3.Q5_K_S.gguf new file mode 100644 index 0000000..84f3b35 --- /dev/null +++ b/BehChat-v0.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9d4cbe6463fbede0d93f9ce7b0b78206398ab35967df0f96f960ff095eefcd +size 5720763488 diff --git a/BehChat-v0.3.Q6_K.gguf b/BehChat-v0.3.Q6_K.gguf new file mode 100644 index 0000000..cc91bd7 --- /dev/null +++ b/BehChat-v0.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7595edf749f830feaa3abfd3e5b1fe270ba3602905fd132f57dd98008d33e6 +size 6725901408 diff --git a/BehChat-v0.3.Q8_0.gguf b/BehChat-v0.3.Q8_0.gguf new file mode 100644 index 0000000..b353aa1 --- /dev/null +++ b/BehChat-v0.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6394ac11bdc0de5111aa650c4f3a8873622b2efd6209cd13f7593010b58464 +size 8709520480 diff --git a/BehChat-v0.3.f16.gguf b/BehChat-v0.3.f16.gguf new file mode 100644 index 0000000..2025bdf --- /dev/null +++ b/BehChat-v0.3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3371e6fe2b30fdcecc47bbfac2ed4ea392df6a33476c694a22f62e1a5d69144 +size 16388045920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2ce7dc9 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: zypchn/BehChat-v0.3 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zypchn/BehChat-v0.3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BehChat-v0.3-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v0.3-GGUF/resolve/main/BehChat-v0.3.f16.gguf) | f16 | 16.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +